Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    performance measurement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     나타
    -0.07
     Hawk
    -0.06
     Bamboo
    -0.06
    ǿ
    -0.06
    ntp
    -0.06
    休
    -0.06
    -theme
    -0.06
     goes
    -0.06
    内陆
    -0.06
     Span
    -0.06
    POSITIVE LOGITS
    住房和城
    0.07
     bringen
    0.07
     נוספת
    0.07
    arians
    0.07
    רב
    0.07
    >Description
    0.06
    .iteritems
    0.06
     Gutenberg
    0.06
    кие
    0.06
     promin
    0.06
    Act Density 0.016%

    No Known Activations